Upload file content

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only convey readOnly=false, idempotent=false, openWorld=true. The description adds substantial context beyond that: the dual create/replace behavior, the retry-duplicate hazard, the 5 MB multipart cap, the precedence rule that name/parent_id are ignored in replace mode, and the convert_to-to-export_file round trip — all behavioral traits the agent could not infer from annotations alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and near-zero waste: five sentences cover the split modes, byte source constraint, mime defaults, conversion, size cap, and retry safety. Small deduction because a few phrases (mime defaults, exactly-one constraint) restate what the input schema already documents rather than adding new information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex dual-mode tool with 7 params, zero required params in the schema, and no output schema, the description covers all invocation risks: mode disambiguation, conditional requirements, size limit, conversion semantics, and duplicate prevention. The only gap is the return contract — 'returns the file's metadata' names the payload but not its fields, notably the file id, which matters because no output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema's per-parameter descriptions already state 'required when creating' and 'Exactly one of content/local_path'. The description adds interaction-level semantics the flat schema cannot express — name/parent_id ignored when file_id is present, convert_to producing native Google files, and the 5 MB bound — though some mime_type default text duplicates the schema, so it stops short of a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource: 'Uploads content to Drive and returns the file's metadata.' It then discretely separates the create mode (no file_id, name required) from the replace mode (file_id, same id, new bytes), which clearly distinguishes it from siblings like download_file, export_file, copy_file, and update_file_metadata.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing to alternatives is present: 'export back with export_file' for converted files, 'larger files need a resumable session via raw_request' past the 5 MB cap, and 'search_files first' before retrying an ambiguous create. Naming the sibling and the condition that selects it leaves nothing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.